EmbeddingGemma - 300M

Name: EmbeddingGemma - 300M
Author: Google Deep Mind

Embedding modelEmbeddingGemmaEmbeddingGemma

Release date: 2025-09-05Updated: 2025-09-06Views: 962

Live demoGitHubHugging Face Compare

Parameters

300M

Context length

Multilingual

Supported

Reasoning ability

3/5

EmbeddingGemma - 300M is an AI model published by Google Deep Mind, released on 2025-09-05, for Embedding model, with 300M parameters, and 2K context length, requiring about 1.21GB storage, with a 61.15 score on MTEB.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

EmbeddingGemma - 300M

Model basics

Reasoning traces

No data

Thinking modes

Standard Mode (Default)Thinking Mode

Context length

2K tokens

Max output length

768 tokens

Model type

Embedding model

Modality (in / out)

Text → Embedding

Release date

2025-09-05

Model file size

1.21GB

MoE architecture

Yes

Total params / Active params

300M / 300M

Knowledge cutoff

No data

EmbeddingGemma - 300M

Open source & experience

Code license

Gemma Terms of Use

Weights license

Gemma Terms of Use- Commercial use permitted

GitHub repo

N/A

Hugging Face

huggingface.co/google/embeddinggemma-300m

Live demo

N/A

EmbeddingGemma - 300M

Official resources

Paper

DataLearnerAI blog

EmbeddingGemma - 300M

API details

API speed

4/5

No public API pricing yet.

EmbeddingGemma - 300M

Benchmark Results

EmbeddingGemma - 300M currently shows benchmark results led by MTEB (5 / 5, score 61.15). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.